Palo Alto Networks' Unit 42 disclosed a vulnerability in Google Cloud's Python SDK for Vertex AI that allowed attackers to intercept machine learning model uploads and swap in a malicious model within roughly two seconds. Google has already shipped a fix through its bug bounty program, and no evidence of exploitation in the wild has been found.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.